Hugging Face's logo

furiosa-ai
/
Llama-3.3-70B-Instruct-INT8

Text Generation
English
furiosa-llm
llama
furiosa-ai
llama-3
conversational
Model card Files
xet
Community
hyunsikc commited on
Commit
005c1fe
·
verified ·
1 Parent(s): e5a4a9b

Delete files * with huggingface_hub

Browse files
Files changed (40) hide show
  1. 04a5823ad7e14ffbca1156f9a6178cdd.edf +0 -3
  2. 11bf9874d6f9f8a4d86a63b57f68a35d.edf +0 -3
  3. 13f857c322fad9ef7b55f1b1086dda09.edf +0 -3
  4. 183bdc182b9bdb1d7447b36c05e55d0e.edf +0 -3
  5. 23f34d7b5db10a1699aae97046022bba.edf +0 -3
  6. 2615a50b61a7353093cf98b7a896c31d.edf +0 -3
  7. 275e4a6d54207ea0590204a4a0d153b6.edf +0 -3
  8. 28582467802d080fa6d658a8fa6a9f34.edf +0 -3
  9. 2c9e189f8475bd64b9fd0e3d60882d17.edf +0 -3
  10. 2d209d27a3cb7bd0072b8796ecc35fb7.edf +0 -3
  11. 33ba2e26b62d709fa0b45e1f9c3d7de5.edf +0 -3
  12. 354c3a6022efd70e119cc96f16f70727.edf +0 -3
  13. 522576220653f06e28cfd1a4a3acb76d.edf +0 -3
  14. 52e1948afd7bd0c125b0e9890309a96e.edf +0 -3
  15. 550dd8a9d847168a63d205f33571f405.edf +0 -3
  16. 5ea0f2ed58c54d9522753e49dbf09794.edf +0 -3
  17. 65e95f29cdd898daa62a57a292c3b59b.edf +0 -3
  18. 671f9e184ad7d3bba644247458a54ed1.edf +0 -3
  19. 6c9ec5658701bdad6060cb8e89362242.edf +0 -3
  20. 724f34a5c07d8f35b48221de0536600f.edf +0 -3
  21. 77a507cb1b75fcced8ab83d582a692f0.edf +0 -3
  22. 77c28d34e99e00ba884ead27527514aa.edf +0 -3
  23. 92b3f0b3dca70ad4197f768f9bf35258.edf +0 -3
  24. 9b6289f395d9fbf410e7d8f59ea9a462.edf +0 -3
  25. a95b577a513fd463209f870517fd8489.edf +0 -3
  26. add_const_file-Quantized_furiosa_llm_models.llama3.symbolic.aramco_specdec.LlamaForCausalLM-kv0-b1-attn640-0.safetensors +0 -3
  27. add_const_file-Quantized_furiosa_llm_models.llama3.symbolic.aramco_specdec.LlamaForCausalLM-kv4095-b1-attn4096-0.safetensors +0 -3
  28. add_const_file-Quantized_furiosa_llm_models.llama3.symbolic.aramco_specdec.LlamaForCausalLM-kv8191-b8-attn8192-0.safetensors +0 -3
  29. b13f5984d766234758871b8bdb0f98eb.edf +0 -3
  30. b6267f79744dacdb08367fecb850257d.edf +0 -3
  31. bbd143788ee50cdbae5b5a8272e0984c.edf +0 -3
  32. c1539fc060ee96d029e7b90f7b2b389c.edf +0 -3
  33. c3a0903ae7f1ddd3d72f2997bb314f47.edf +0 -3
  34. ca2f6ca3a06117ec674d6e39498f2c63.edf +0 -3
  35. config.json +0 -41
  36. d3c2d9f6a53838924ea90dfeb8f014f0.edf +0 -3
  37. df3d9416fd7e9f0ceae79f8039ff81da.edf +0 -3
  38. e07d9f490ede29dd1a32ddad2f611600.edf +0 -3
  39. e0aa0e5ae3b05578ea10e893c70a1a38.edf +0 -3
  40. furiosa_config.json +0 -58
04a5823ad7e14ffbca1156f9a6178cdd.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a95a40e1124f6ae65019a434845a95d03a27422a28e6e38b2a95205f5b2bf0d
3
- size 17925559
 
 
 
 
11bf9874d6f9f8a4d86a63b57f68a35d.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d29bbda81e3cc2902ac0190d995ac31caf456cd29e06df12b976ba93a4c4b34
3
- size 5014042
 
 
 
 
13f857c322fad9ef7b55f1b1086dda09.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a909a68c175bdfb2c3393d18d164b38cd01eb83baeaf3311eadc956edf19650e
3
- size 26463927
 
 
 
 
183bdc182b9bdb1d7447b36c05e55d0e.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b9fa7a908e2f4b040e969667e22962a39a4d3728970ac59c784b07713278c6e
3
- size 14686651
 
 
 
 
23f34d7b5db10a1699aae97046022bba.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2d9228f679729613de5d95858aca504b43225c3b4b63097bdb7e468c4ae7c2b
3
- size 5467481
 
 
 
 
2615a50b61a7353093cf98b7a896c31d.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ba3b47c61404794e7212372d862c40fc045679d6bc2858b902b81ce47ee1ad8
3
- size 4928665
 
 
 
 
275e4a6d54207ea0590204a4a0d153b6.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d259b6f727657b02876e83a4baf6d8c4e7bc4bc9fd9934c141dc8b789b55c2bc
3
- size 5103526
 
 
 
 
28582467802d080fa6d658a8fa6a9f34.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:731e3601d941f72796c1e955b4e547d3e12286f9c827b9c0a6e352852c95dda8
3
- size 4870090
 
 
 
 
2c9e189f8475bd64b9fd0e3d60882d17.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:821312b6f7510883d0dc882b4c2dd3fcb68579ad3f9cd81098bb909ecdac8142
3
- size 5261266
 
 
 
 
2d209d27a3cb7bd0072b8796ecc35fb7.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f423aff43d64515045127d97a485c374f7444a7c4fe32d32fb35c17d19eb7d2
3
- size 7028958
 
 
 
 
33ba2e26b62d709fa0b45e1f9c3d7de5.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:225e8137d5b6c7a8baa6907f7b6ad50848b089a14d4258ee1fdbaa4763df37d3
3
- size 12066649
 
 
 
 
354c3a6022efd70e119cc96f16f70727.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9e99fc3f0cf0cfdf0e3bd42bcf2f4e5cc9ab5c17b6b65d67e8a4ebd22a91b98
3
- size 21587241
 
 
 
 
522576220653f06e28cfd1a4a3acb76d.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bd071072c302d3b42ffdf049801e165a80bc93edd4682f2704954fd1500fc8e
3
- size 12000971
 
 
 
 
52e1948afd7bd0c125b0e9890309a96e.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bff7420aaf04cc741189e5240f511652e4cba3193c46853a4cc9d8909cbdbb7c
3
- size 4896703
 
 
 
 
550dd8a9d847168a63d205f33571f405.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac0564e1fd4b367b634e081da22a2d122260b099b4f8fe162532e4356a23890e
3
- size 5963770
 
 
 
 
5ea0f2ed58c54d9522753e49dbf09794.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7da3056808f6da3d4773e72a543932945ebe018157fdebf92c81a14d303b9bc8
3
- size 4941234
 
 
 
 
65e95f29cdd898daa62a57a292c3b59b.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9f3155c1a391cc834b8a830e307dee691f4ca7d69fed04cecf1ed61fb5dea67
3
- size 5297866
 
 
 
 
671f9e184ad7d3bba644247458a54ed1.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a915682e3aa2e831d32518e8c7ba7fa7ac39e4396dfeae58ec7a243ef6482231
3
- size 34928253
 
 
 
 
6c9ec5658701bdad6060cb8e89362242.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:53b1956b91bc181c26b256a6ccd15e33b0d040a6a558c62da7523181ed3445e1
3
- size 5232534
 
 
 
 
724f34a5c07d8f35b48221de0536600f.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e4ce54227d72a0f2f6387553ec8d88f3f616546b57d067c866280528e10c566
3
- size 6023594
 
 
 
 
77a507cb1b75fcced8ab83d582a692f0.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a69ce45112750f5be2d056c24f0fe733a9782b2ae8b8ded4958d1933c773a96e
3
- size 6235972
 
 
 
 
77c28d34e99e00ba884ead27527514aa.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:23392bda5a7f8ace8185abb639715749e1ea80e0719c7b65addd26d5d1025870
3
- size 19538043
 
 
 
 
92b3f0b3dca70ad4197f768f9bf35258.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e58cf3b9d41d243f74dd001d3d71f92666d439c49fe38ed00d4b457095876a3
3
- size 5826474
 
 
 
 
9b6289f395d9fbf410e7d8f59ea9a462.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7faf22a84566bdac7f0bc588c7fa281d81be2b81ba0d923619b605f12a05c75a
3
- size 5781803
 
 
 
 
a95b577a513fd463209f870517fd8489.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c365cf386b1e4fe1e92deebd0b7e1e69e484016e82120bc0e78c1dc4b853d53e
3
- size 19766670
 
 
 
 
add_const_file-Quantized_furiosa_llm_models.llama3.symbolic.aramco_specdec.LlamaForCausalLM-kv0-b1-attn640-0.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:50664b6d3d0ec308fd27956f20e50da2dcb26a8d38edb485e3c42b2f181960b7
3
- size 26953104
 
 
 
 
add_const_file-Quantized_furiosa_llm_models.llama3.symbolic.aramco_specdec.LlamaForCausalLM-kv4095-b1-attn4096-0.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:50664b6d3d0ec308fd27956f20e50da2dcb26a8d38edb485e3c42b2f181960b7
3
- size 26953104
 
 
 
 
add_const_file-Quantized_furiosa_llm_models.llama3.symbolic.aramco_specdec.LlamaForCausalLM-kv8191-b8-attn8192-0.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:50664b6d3d0ec308fd27956f20e50da2dcb26a8d38edb485e3c42b2f181960b7
3
- size 26953104
 
 
 
 
b13f5984d766234758871b8bdb0f98eb.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:293c2c4af97bf258990e65c65b0ec44c031afd6dfe8189de07c1514fdcffcdd9
3
- size 11670652
 
 
 
 
b6267f79744dacdb08367fecb850257d.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7efcdffaf36a3a7f5dea470cfe27a3d75ba8186672b07bd657390a3b8117834a
3
- size 34286137
 
 
 
 
bbd143788ee50cdbae5b5a8272e0984c.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:83a4f89c097b03c77246efcb4c21b60ca6df41723e41619c58d728563173d011
3
- size 5920284
 
 
 
 
c1539fc060ee96d029e7b90f7b2b389c.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f474633c052c5a48c94a9b6b64a8b5a57477a173101a07c7e95f479839caf6c
3
- size 6424210
 
 
 
 
c3a0903ae7f1ddd3d72f2997bb314f47.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ddbce01f69c8afa9b0ff4a783a99e479d793b9b2122bff72d7f68ae7450cecf
3
- size 5272037
 
 
 
 
ca2f6ca3a06117ec674d6e39498f2c63.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:07c93106cf0ade1e2ea5a5e60af04a35cbedaa283c18a90ce488eeb62068d0c7
3
- size 34218010
 
 
 
 
config.json DELETED
@@ -1,41 +0,0 @@
1
- {
2
- "_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": [
10
- 128001,
11
- 128008,
12
- 128009
13
- ],
14
- "head_dim": 128,
15
- "hidden_act": "silu",
16
- "hidden_size": 8192,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 28672,
19
- "inv_freq_config": {
20
- "factor": 8.0,
21
- "high_freq_factor": 4.0,
22
- "low_freq_factor": 1.0,
23
- "original_max_position_embeddings": 8192,
24
- "rope_type": "llama3"
25
- },
26
- "max_position_embeddings": 131072,
27
- "mlp_bias": false,
28
- "model_type": "llama",
29
- "num_attention_heads": 64,
30
- "num_hidden_layers": 80,
31
- "num_key_value_heads": 8,
32
- "pretraining_tp": 1,
33
- "rms_norm_eps": 1e-05,
34
- "rope_scaling": null,
35
- "rope_theta": 500000.0,
36
- "tie_word_embeddings": false,
37
- "torch_dtype": "bfloat16",
38
- "transformers_version": "4.48.1",
39
- "use_cache": true,
40
- "vocab_size": 128256
41
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d3c2d9f6a53838924ea90dfeb8f014f0.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:92dda4af740dcdbb12063cb1ae347aebe72d3129730d4b1126f82e3c7c2dabd4
3
- size 6054044
 
 
 
 
df3d9416fd7e9f0ceae79f8039ff81da.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a0648351484ff57e87348fdef7b1b1cd462174e75f0d889767a2f833e68b291
3
- size 17811146
 
 
 
 
e07d9f490ede29dd1a32ddad2f611600.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:040ab23ef10dc840c168300deaa7bddaa25f6adc983b8f03e62a8b9bfdcc8153
3
- size 9667382
 
 
 
 
e0aa0e5ae3b05578ea10e893c70a1a38.edf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2571d92170191b48f1f130691327fc693e5c466eae4042142c7643b30a3a4027
3
- size 22311988
 
 
 
 
furiosa_config.json DELETED
@@ -1,58 +0,0 @@
1
- {
2
- "config_version": "1.0.0",
3
- "model_id": "meta-llama/Llama-3.3-70B-Instruct",
4
- "model_kinds": [
5
- "ARTIFACT"
6
- ],
7
- "model_class": {
8
- "module": "furiosa_llm_models.llama3.symbolic.aramco_specdec",
9
- "name": "LlamaForCausalLM"
10
- },
11
- "llm_config": {
12
- "optimization_config": {
13
- "attention_type": "PAGED_ATTENTION",
14
- "optimize_rope": true,
15
- "optimize_packed": true,
16
- "decompose_layernorm": false,
17
- "optimize_furiosa": false,
18
- "use_unsplit_packed": false,
19
- "compact_causal_mask": false,
20
- "use_rngd_gelu": false,
21
- "causal_mask_free_decoding": true,
22
- "kv_cache_sharing_across_beams": false,
23
- "inbound_beamsearch_softmax": false,
24
- "calculate_logit_only_for_last_token": false,
25
- "optimized_for_speculative_decoding": true,
26
- "use_2d_masks": false,
27
- "merged_kv_indices": false
28
- },
29
- "quantization_config": {
30
- "weight": "int8",
31
- "activation": "bf16",
32
- "kv_cache": "bf16",
33
- "use_mcp": true
34
- }
35
- },
36
- "components_versions": {
37
- "furiosa_llm": {
38
- "version": "0.1.0-dev",
39
- "git_hash": "834ab61",
40
- "build_time": null
41
- },
42
- "furiosa_ir": {
43
- "version": "0.11.0-dev",
44
- "git_hash": "8c5160b804",
45
- "build_time": "2025-07-30T04:02:12Z"
46
- },
47
- "furiosa_runtime": {
48
- "version": "2025.3.0",
49
- "git_hash": "834ab6188",
50
- "build_time": "2025-07-30T04:04:26Z"
51
- },
52
- "furiosa_model_compressor": {
53
- "version": "2025.3.0 (rev: 4cd9804)",
54
- "git_hash": null,
55
- "build_time": null
56
- }
57
- }
58
- }